How to Use the GameScorekeeper MCP in LlamaIndex

Q: How do I use GameScorekeeper tools in my LlamaIndex RAG setup?

You wrap the GameScorekeeper MCP client in a McpToolSpec. This exposes all the tools, like listfixtures, which you can then pass to a FunctionAgent to query live sports data.

Q: What's a good workflow for GameScorekeeper and LlamaIndex?

A common pattern is to periodically run tools like listcompetitions and listfixtures to populate your index. Then, for user queries, the agent can use getfixturedetails for real-time info and query the index for historical context.

Index live sports data with LlamaIndex. Ground your RAG app in real-time fixture details, player stats, and team forms.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GameScorekeeper MCP to LlamaIndex

Create your Vinkius account to connect GameScorekeeper to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup GameScorekeeper with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn API Calls into a Knowledge Base

Don't just fetch data, index it. Use the GameScorekeeper tools to pull information with `list_competitions` or `get_player_details`, and LlamaIndex automatically adds the results to a vector index. Now your agent can query past results without making another API call. This builds a persistent, searchable memory for your agent. Ask about a fixture from last week, and it can pull the answer from the index using a `get_fixture_details` call it made days ago. It's how you build context-aware sports applications.

Ground Answers in Verifiable Sports Data

Stop your agent from making things up about game outcomes. With LlamaIndex, every answer is grounded in data from a GameScorekeeper tool. It can cite the source, showing it used `get_player_stats` or `get_team_form` to find the answer. This is key for building trust. When your RAG app says a player is in top form, it can prove it by pointing to the indexed results of `get_team_form`, showing the recent win/loss record. This MCP server is your source of truth.

Query Live and Historical Data in LlamaIndex

Combine live API calls with your indexed knowledge. LlamaIndex can query your document store for historical context and then make a live call to `get_fixture_lineup` to check tonight's roster. This creates a powerful research agent. It can compare a team's current lineup from `get_fixture_lineup` against its performance over the last season, which you've already indexed. You get the best of both static and live data.

Setup guide

Set up GameScorekeeper MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all GameScorekeeper MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to GameScorekeeper tools.",
)
response = await agent.run("List recent GameScorekeeper data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by GameScorekeeper. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect GameScorekeeper now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about GameScorekeeper MCP in LlamaIndex

You wrap the GameScorekeeper MCP client in a `McpToolSpec`. This exposes all the tools, like `list_fixtures`, which you can then pass to a FunctionAgent to query live sports data.

Yes, that's the whole point. When LlamaIndex uses a tool like `get_player_stats`, it can index the response. Future queries can then hit this local index instead of the live API, which is faster and saves on API calls.

A common pattern is to periodically run tools like `list_competitions` and `list_fixtures` to populate your index. Then, for user queries, the agent can use `get_fixture_details` for real-time info and query the index for historical context.

Absolutely. You can have an index built from your own PDFs or text files, and the agent can query both that index and the live GameScorekeeper tools in the same session to get a complete answer.

Yes. GameScorekeeper only handles public sports data like fixture lineups and team forms. Your API calls are processed in isolated sandboxes on Vinkius, and no personally identifiable user data from your end is ever sent or stored.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript